Three-dimensional grid simplifying method and device, electronic equipment and storage medium

Abstract

The invention relates to a three-dimensional grid simplifying method and device, electronic equipment and a storage medium. The method comprises the steps: acquiring a three-dimensional grid model of a target object, and converting the three-dimensional grid model into a two-dimensional grid image, wherein the three-dimensional grid model comprises a plurality of three-dimensional triangles; obtaining a two-dimensional mask image, wherein the size of the two-dimensional mask image is the same as that of the two-dimensional grid image, the two-dimensional mask image comprises a target mask area; determining a two-dimensional target area corresponding to the target mask area in the two-dimensional grid image, wherein the two-dimensional target area comprises a plurality of two-dimensional target triangles; and determining a three-dimensional target triangle corresponding to the two-dimensional target triangle in the three-dimensional grid model, and taking a three-dimensional grid formed by the three-dimensional target triangle as a simplified three-dimensional simplified grid. According to the scheme, the three-dimensional grid of the human face can be effectively simplified, and the refined beauty makeup special effect on the specific area can be achieved in various scenes.

Description

technical field [0001] The present disclosure relates to the field of image processing, and in particular to a simplified method, device, electronic equipment and storage medium for a three-dimensional grid. Background technique [0002] At this stage, smart terminals such as mobile phones and tablet computers often provide users with special effects for specific objects, such as three-dimensional beauty filters and virtual characters, during the process of shooting or playing videos. Taking 3D cosmetic special effects as an example, it usually needs to establish a 3D grid model for the face, and then render based on the grid to obtain 3D cosmetic special effects and display them. However, because the 3D mesh model often has a large number (such as 10,000) of 3D mesh vertices in order to achieve a richer detail display effect, the refined rendering puts forward higher requirements on the performance of the device, and often results in The device gets hot, the program freeze...

AI Technical Summary

Problems solved by technology

Although this method solves the problem of local refinement, due to the use of a fixed 3D face local mesh, the simplified mesh will not change with the real face changes, for example, when the mouth is opened and closed, The rendering results are the same, so this solution can only be applied to some fixed beauty scenes, and the versatility is poor

Images